Implementations generally relate to determining tool handedness for surgical videos. In some implementations, a method includes receiving at least one image frame of a plurality of image frames. The method further includes detecting one or more objects in the at least one image frame. The method further includes classifying the one or more objects into one or more tool classifications, where the one or more objects are tools. The method further includes determining, for each tool, if the tool is assistive or non-assistive. The method further includes determining, for each tool, a handedness of the tool.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A system comprising: one or more processors; and logic encoded in one or more non-transitory computer-readable storage media for execution by the one or more processors and when executed operable to perform operations comprising: receiving at least one image frame of a plurality of image frames; detecting one or more objects in the at least one image frame; classifying the one or more objects into one or more tool classifications, wherein the one or more objects are one or more tools; determining a handedness of each tool of the one or more tools based on a position of each tool in the at least one image frame; and identifying at least one dominant tool and at least one assistive tool from the one or more tools based on the handedness of each tool, wherein a dominant handedness is associated with the at least one dominant tool, and wherein a non-dominant handedness is associated with the at least one assistive tool.
2. The system of claim 1 , wherein the logic when executed is further operable to perform operations comprising determining a type confidence score, and wherein the type confidence score indicates an accuracy level of the classifying of the one or more objects into the one or more tool classifications.
3. The system of claim 1 , wherein the logic when executed is further operable to perform operations comprising identifying features of each of the tools, and wherein the features include one or more of shape, orientation, and color.
4. The system of claim 1 , wherein the determining if each of the tools is assistive or non-assistive is based at least in part on a type of tool.
5. The system of claim 1 , wherein the logic when executed is further operable to perform operations comprising labeling each tool in the at least one image frame with the handedness of each tool.
6. The system of claim 1 , wherein the determining of the handedness of each of the tools is based at least in part on deep learning.
7. The system of claim 1 , wherein the logic when executed is further operable to perform operations comprising determining a handedness confidence score, and wherein the handedness confidence score indicates an accuracy level of the determining of the handedness.
8. A non-transitory computer-readable storage medium with program instructions stored thereon, the program instructions when executed by one or more processors are operable to perform operations comprising: receiving at least one image frame of a plurality of image frames; detecting one or more objects in the at least one image frame; classifying the one or more objects into one or more tool classifications, wherein the one or more objects are one or more tools; determining a handedness of each tool of the one or more tools based on a position of each tool in the at least one image frame; and identifying at least one dominant tool and at least one assistive tool from the one or more tools based on the handedness of each tool, wherein a dominant handedness is associated with the at least one dominant tool, and wherein a non-dominant handedness is associated with the at least one assistive tool.
9. The computer-readable storage medium of claim 8 , wherein the instructions when executed are further operable to perform operations comprising determining a type confidence score, and wherein the type confidence score indicates an accuracy level of the classifying of the one or more objects into the one or more tool classifications.
10. The computer-readable storage medium of claim 8 , wherein the instructions when executed are further operable to perform operations comprising identifying features of each of the tools, and wherein the features include one or more of shape, orientation, and color.
11. The computer-readable storage medium of claim 8 , wherein the determining if each of the tools is assistive or non-assistive is based at least in part on a type of tool.
12. The computer-readable storage medium of claim 8 , wherein the instructions when executed are further operable to perform operations comprising performing the determining of the handedness in real-time.
13. The computer-readable storage medium of claim 8 , wherein the determining of the handedness of each of the tools is based at least in part on deep learning.
14. The computer-readable storage medium of claim 8 , wherein the instructions when executed are further operable to perform operations comprising determining a handedness confidence score, and wherein the handedness confidence score indicates an accuracy level of the determining of the handedness.
15. A computer-implemented method comprising: receiving at least one image frame of a plurality of image frames; detecting one or more objects in the at least one image frame; classifying the one or more objects into one or more tool classifications, wherein the one or more objects are one or more tools; determining a handedness of each tool of the one or more tools based on a position of each tool in the at least one image frame; and identifying at least one dominant tool and at least one assistive tool from the one or more tools based on the handedness of each tool, wherein a dominant handedness is associated with the at least one dominant tool, and wherein a non-dominant handedness is associated with the at least one assistive tool.
16. The method of claim 15 , further comprising determining a type confidence score, and wherein the type confidence score indicates an accuracy level of the classifying of the one or more objects into the one or more tool classifications.
17. The method of claim 15 , further comprising identifying features of each of the tools, and wherein the features include one or more of shape, orientation, and color.
18. The method of claim 15 , wherein the determining if each of the tools is assistive or non-assistive is based at least in part on a type of tool.
19. The method of claim 15 , further comprising performing the determining of the handedness in real-time.
20. The method of claim 15 , wherein the determining of the handedness of each of the tools is based at least in part on deep learning.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 14, 2018
March 30, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.